Newest papers

SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs

Yifan Yuan, Yancheng Zhu, ZuoYu Zhang, Xiaogang Peng · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31317 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

SurveyGraph, sebuah kerangka kerja yang dibangun di sekitar Methods-Entity Knowledge Graph (MEKG) yang mengkodekan metode-level follow-on, kompetisi, dan hubungan sumber daya bersama-sama. Grafik ini mendukung penemuan kertas inti, penangkapan pada struktur penelitian hibrida, dan sintesis narasi berbasis bukti. Kami mengevaluasi penangkapan, tepi semantik, landasan kutipan, penangkapan koleksi, dan komponen-komponen tahap-generasi. Dalam kontrol tujuh-metode ekvivalent-budget benchmark, grafik MEKG-anchored penangkapan keseimbangan fusi dan kepadatan struktural survei, dengan verifikasi ko-citasi independen. Dalam sebuah arsip terpisah graf-native, organisasi semantik-diagnostik-pengendalian tipe-hybrid,

Machine translation (Meta M2M100); the English original follows.

Abstract

Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-paper discovery, retrieval, hybrid outlining, and evidence-gated narrative synthesis. We evaluate retrieval, semantic edges, citation grounding, collection coverage, and generation-stage components. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion balances recall and structural density, with an independent co-citation check. In a separate archived graph-native diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across eight runs (p = 0.004). A semantic evidence gate achieves AUC = 0.75. Audits of 160 generated sentences find 80.6% anchored-or-partial citation support. Human adjudication of 108 stratified semantic edges finds 68.5% supported-or-partial relations (binary-support Cohen's kappa = 0.64), with improves strongest (80.6%) and extends weakest (52.8%). A SurveyBench-facing collection probe reaches mean reference coverage of 0.521 across four topics with an eight-paper budget. Same-backend Qwen diagnostics on a 30-paper/74-relation graph show reduced organization signals when hybrid outlining is removed. Concurrent-system comparisons provide bounded context rather than matched-backend end-to-end evidence. The results position MEKG as an auditable structural layer for typed diagnostics, relation-specific filtering, and controlled survey generation. Code and artifacts: https://github.com/xzzvsxd/SurveyGraph.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Information retrieval, Graph, Citation, Recall, Context (archaeology)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange